# PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction

arXiv: https://arxiv.org/abs/2302.04488 · HTML: https://mlsanity.com/paper/2302.04488/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2023.

## Built on by (most cited first, 8 of 8)

- [GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction](https://mlsanity.com/paper/2504.21067/) (2025)
- [Pre-NeRF 360: Enriching Unbounded Appearances for Neural Radiance Fields](https://mlsanity.com/paper/2303.12234/) (2023)
- [Bag of Views: An Appearance-based Approach to Next-Best-View Planning for 3D Reconstruction](https://mlsanity.com/paper/2307.05832/) (2023)
- [SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas](https://mlsanity.com/paper/2510.19766/) (2025)
- [MASSTAR: A Multi-Modal and Large-Scale Scene Dataset with a Versatile Toolchain for Surface Prediction and Completion](https://mlsanity.com/paper/2403.11681/) (2024)
- [ExploreGS: a vision-based low overhead framework for 3D scene reconstruction](https://mlsanity.com/paper/2505.10578/) (2025)
- [A 3D Reconstruction Benchmark for Asset Inspection](https://mlsanity.com/paper/2603.17358/) (2026)
- [VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction](https://mlsanity.com/paper/2609.23049/) (2026)

## Abstract (arXiv)

Autonomous UAV path planning for 3D reconstruction has been actively studied in various applications for high-quality 3D models. However, most existing works have adopted explore-then-exploit, prior-based or exploration-based strategies, demonstrating inefficiency with repeated flight and low autonomy. In this paper, we propose PredRecon, a prediction-boosted planning framework that can autonomously generate paths for high 3D reconstruction quality. We obtain inspiration from humans can roughly infer the complete construction structure from partial observation. Hence, we devise a surface prediction module (SPM) to predict the coarse complete surfaces of the target from the current partial reconstruction. Then, the uncovered surfaces are produced by online volumetric mapping waiting for observation by UAV. Lastly, a hierarchical planner plans motions for 3D reconstruction, which sequentially finds efficient global coverage paths, plans local paths for maximizing the performance of Multi-View Stereo (MVS), and generates smooth trajectories for image-pose pairs acquisition. We conduct benchmarks in the realistic simulator, which validates the performance of PredRecon compared with the classical and state-of-the-art methods. The open-source code is released at https://github.com/HKUST-Aerial-Robotics/PredRecon.